© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 114088
    Prev
    Next
    INDEX
    Explanations

    Writing and language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ･
    -0.08
    erti
    -0.08
     kinn
    -0.07
    middlewares
    -0.07
    elem
    -0.07
    Dell
    -0.07
     problemas
    -0.07
    .Aut
    -0.07
    .numpy
    -0.07
     confirms
    -0.07
    POSITIVE LOGITS
     möglichst
    0.13
     aiming
    0.10
     purposely
    0.10
     όσο
    0.10
     loose
    0.09
     deliberately
    0.09
     intentionally
    0.09
     exploratory
    0.09
     Loose
    0.09
     இதில்
    0.09
    Activations Density 0.085%

    No Known Activations